Loading...

Background

111

Centre for Development of Advanced Computing (C-DAC) under the aegis of the National Supercomputing Mission (NSM), a Ministry of Electronics & Information Technology (MeitY) and Department of Science & Technology (DST) initiative, in association with NVIDIA & OpenACC, announces the SAMHAR-COVID19 Hackathon.

Pandemic outbreak such as Coronavirus outbreak can create huge challenges for the Government and Public Health Officials to gather information quickly and coordinate a response. In such a situation, Artificial Intelligence (AI) can play a huge role in predicting, minimizing and stalling its spread of the virus.

C-DAC has embarked on a program SAMHAR-COVID19 (Supercomputing using AI, ML, Healthcare Analytics based Research for combating COVID19). This opportunity will provide researchers to find solutions for Identifying, Tracking and Forecasting outbreaks of COVID19 and Facilitating Drug Discovery as well.

The intention behind this hackathon is not just to solve current Covid-19 situation but to prepare the research community to make use of HPC-AI tools and keep ready to predict outbreaks like this. The hackathon is open to Researchers, Academicians, MSMEs, Startups and Industries with an objective to bring out Innovative and Implementable Ideas for Prediction, Forecasting and Building Healthcare Models that could revolutionize the way we interpret science of pandemic outbreaks using AI technology on Supercomputers.

The problems related to COVID19 that will be solved during this Hackathon are as follows:

  • Drug Discovery and Genome Sequencing: Human Genome is complex and has 3.2 billion base pairs. India became the fifth country in the world to sequence the genome of the novel Coronavirus, or COVID19, and share its data with the international community. Genome data is essential to build tests, find drugs and vaccines.
  • Medical Imaging: AI has proven accuracy to detect patterns from Images. Healthcare images like CT provide crucial information and can be used to detect Corona Virus.
  • Contactless Monitoring: To Explore Contactless monitoring of the outbreak, to explore usage of drones to help medical staff to transport medical samples and to conduct thermal imaging.
  • Surveillance and Monitoring: Use of Computer Vision Techniques to automate monitoring crowd gathering or tracking possible carriers by looking at patterns like sneezing etc.
  • Forecasting: Predict the cumulative number of confirmed COVID19 cases in various locations across India, as well as the number of resulting fatalities using various datasets from the states and union territories of India combined with Big-Data information available from Social Media.
  • Data Mining: There are more than 44000 research articles on COVID19 already published and the numbers are growing. Use of AI and data analytics techniques to come out with solutions to help the medical community to analyze news reports and online content from around the world to recognize anomalies and predict critical events.

To summarize SAMHAR-COVID19 Hackathon aims to find solutions with the following priorities (but not limited to these only):

  1. To achieve better (More Accurate) and Faster Turnaround time for Testing and results.
  2. To identify, track and forecast outbreaks.
  3. To develop Drug Re-purposing Simulations leading to New Drug Discovery.
  4. To develop the Simulations/Solutions using Traditional (AYUSH) Medicines.
  5. To create Chat Bot with multiple regional language supporting Conversational AI Techniques.
  6. To develop AI based identification of non-complying or infected individuals.
  7. To create, Train and Deploy Robots to sterilize, Deliver Food and Supplies.
  8. To deploy Drones to monitor sites, announce policy measures and to deliver medical supplies in the infected regions/areas.
  9. To enable automation of COVID 19 Health care Claims for Ayushman Bharat Program

SAMHAR-COVID19 Hackathon

Innovative Implementable Idea (I3) Award

Participants will not only contribute to this hackathon for Noble Cause, but will also have opportunities to win awards. The Hackathon will be conducted in two rounds:

In Round-1, the top 25 Innovative Implementable Ideas will be selected by an Eminent Jury comprising of eminent scientists and domain experts.

The proposers of these selected ideas will move to Round-2 for proving their Ideas by building a prototype for establishing the Proof of Concept. The proposers are required to demonstrate their prototypes and make presentations to the Eminent Jury during the prescribed period.

In Round-2, the participants will be provided with:

  • Compute Infrastructure: Access to PARAM Series of Supercomputing facility established under NSM (PARAM-Shivay, PARAM-Brahma and PARAM-Shrishti including PARAM-Shrestha and PARAM-Sangam) and to the latest NVIDIA Tesla GPU powered systems will be provided through National Knowledge Network (NKN) backbone.
  • Datasets: Access to India specific datasets or sample data sets (on request).
  • Training: Participants will be provided training on latest HPC-AI tools including C-DAC Tools like: TANGO: Small drug like molecular conformation generation and energy optimization to find right postures of small molecules in the database; HBAT: Big-data Analytics tool to Find hydrogen bonds in the simulation trajectories and water interactions; Parabricks: Genome Sequencing Toolkit; RAPIDS: Machine learning Library; DeepStream SDK:Streaming Analytics Toolkit; and AI GPU libraries from NVIDIA (wherever applicable).
  • Mentorship: Mentors from C-DAC, Industry and Research Organization will guide the participants to help achieve optimal results during the course of Hackathon.

Awards

In Round-1, the selected Innovative Implementable Idea (I3) Award entry (irrespective of the number of members in the team) will be rewarded with Cash Award of Rs. 10,000 (Rs. Ten Thousand) each and a 'Certificate of Appreciation'.

In Round-2, the Top 6 Innovative Implementable Idea (I3) Awards will be given away by C-DAC under NSM as described below:

  • Outstanding Innovative Implementable Idea (One Award):
    Award will consist of a ‘Citation’ +
    A Cash award of Rs. 2,00,000.00 (Rs. Two Lakhs only) +
    Free 500 Hours* of CPU-GPU Computing Credits along with upto 200TB Storage on PARAM Series of Supercomputing facilities established under NSM and the 100 AI PF PARAM Siddhi-AI Supercomputer connected through NKN;

  • Excellent Implementable Idea (Two Awards):
    Award will consist of a ‘Citation’ +
    A Cash award of Rs. 1,00,000.00 (Rs. One Lakhs only) +
    Free 300 Hours* of CPU-GPU Computing Credits along with upto 100TB Storage on PARAM Series of Supercomputing facilities established under NSM and the 100 AI PF PARAM Siddhi-AI Supercomputer connected through NKN;

  • Promising Innovative Implementable Idea (Three Awards):
    Award will consist of a ‘Citation’ +
    A Cash award of Rs. 50,000.00 (Rs. Fifty Thousand only) +
    Free 200 Hours* of CPU-GPU Computing Credits along with upto 50TB Storage on PARAM Series of Supercomputing facilities established under NSM and the 100 AI PF PARAM Siddhi-AI Supercomputer connected through NKN;

Terms of Participation and Awards

  • Participants can update submissions multiple times till the Registration End date.
  • Each entry can be submitted by a Team comprising of minimum 3 and maximum 5 members (Including the Team Lead).
  • Participants will have to share the complete work activities with C-DAC. And C-DAC will have right to use the submitted application/solution for SAMHAR-COVID19 programs.
  • The Award will be given to the Selected/Winning Entry irrespective of the number of members in the Team (members may choose to distribute the amount among themselves).
  • The decision of the Eminent Jury on the I3 Award will be final and binding.
  • Award can be for the Team/Company/Institution, as submitted in the Application and cannot be changed later.
  • Submissions will be considered void if they are in whole or part ill-eligible, incomplete, damaged, altered, counterfeit, obtained through fraud or late submission.

Timelines

Round-1: 1st - 25th April 11th May 2020

  • Launch/Announcement: 1st April 2020
  • Application registrations start date: 6th April 2020
  • Application registrations close date: 20th April 8th May 2020
  • Shortlist of Applications for Round-2: 25th April 11th May 2020

Round-2: 30th April 12th May to 15th 25th May 2020 (Data Sets will be provided on request)

  • Computing Resources and Mentors allocation: 30th April 12th May 2020
  • CPU-GPU Boot Camp: 1st 12th May, 2020
  • Hackathon period: 30th April 12th May to 15th 25th May 2020
  • Teams working with mentors: 30th April 12th May - 15th 25th May 2020
  • Hackathon Presentations: Teams Demonstrate and Present final projects 16th 26th May to 20th 29th May 2020

Award Winners Announcement: 28th 31st May, 2020 with awards to be given during the 'C-DAC Tech Conclave 2020' in a grand function.

Registration

 

Registration closed

 

Send your queries to SAMHAR-COVID19Hackathon@cdac.in

Results

SAMHAR-COVID19 Hackathon Winners (31st May 2020)


Teams Qualified for Stage-2

  • CLASP
  • Pymetrics
  • Team BHU
  • Team McMarvin
  • AI for Good
  • TCS Tridents
  • Gateware
  • Greenojo
  • Imagers
  • Sanjeevani
  • Sequence based classifier
  • IISERB
  • Drug discoverers
  • Coeus
  • Pandemiculator
  • SocioTechies
  • Zauberer
  • Corona Fighter
  • AlphaClan
  • A.Eye
  • Brutus
  • Decovit
  • EagleEye
  • Delta
  • Autonom

FAQ

Related to Acceptance/Rejection/Winning the competition

Q. How do I know if I have been accepted or rejected in Round 1 and Round 2?

A. You will receive mailer and the status of accept and rejection will be displayed on the website for respective rounds. Round 1 shortlisting announcement will be done on 25th April 2020 and Round 2/Final winner announcement will be done on 28th May 2020.

Q. I see my application has been declined after submission before even Round 1 announcement?
What was the reason?

A. Application forms are carefully reviewed to and decisions are taken based on the fields entered during the registration for event. If reviewers note that some of the fields entered does not look valid like email id, profile details, unique team members etc. they may reject the application.

Q. I submitted my application, but I see the status as pending? What does that mean?

A. After the application is submitted the reviewers goes through the submission and accepts/ declines it based on the details filled during registration. This may take a day so be patient with us. If the application is not accepted or rejected in a days' time, please write back to us on given contact email id

Q. What is the criteria for selecting the winners?

A. The submissions will be judged on the following metrics by the reviewers and Jury members:

  • Contextual Relevance: High impact to Indian scenario solving Covid-19 challenges
  • Technological Superiority: Use of latest technology and trends, better performance and accuracy.
  • Innovation Quotient: Innovative with high research quotient and potential to become unique solution
  • Viability: The solution is practically feasible in real world scenario considering the cost to solution, ease of integration into existing infrastructure and easy deployment in the field.
  • Team Participation: The team should be able to demonstrate the expertise as given in the application.
    The decision of the Jury on the I3 Award will be final and binding.

Q. Will I be given an explanation on why my application did not win in Round 1 and Round 2?

A. The application submission gets evaluated by multiple reviewers and their comments are documented. If required, you can ask your queries to organizers and we can provide based on case to case basis. But please note the reviewers and Jury member are experts in this domain and their decision will be considered as final.

General Queries

Q. What is maximum and minimum number of team members required for participation?

A. Team should compromise of minimum 3 and maximum 5 members (Including the Team Lead)

Q. Who owns the solution of the Hackathon?

A. While the participating team owns the solution, all the participants will have to share the solution with C-DAC. And C-DAC will have right to use the winner application/solution for SAMHAR-COVID19 programs.

Q. Who can participate in this Hackathon?

A. The hackathon is open to Researchers, Academicians, MSMEs, Startups and Industries having an Indian establishment.

Related to Stages of Hackathon

Q. What is difference between Round 1 and Round 2

A. In round 1 teams can submit theoretical solution based on their understanding of the problem statement and open source data provided to them. They are free to also give a working solution (though not mandatory) which increases their chance of acceptance. In round 2 selected teams will be given training on latest AI stack, provided with mentors who are expert in this field, compute resources and additional local dataset (on ask basis) to realize the problem statement

Related to Stages of Hackathon

Q. Can I submit my own problem statement which does not match with the pre-defined problem statement?

A. Yes you may. You can choose in the Application submission form dropdown "Other/Open House Challenge" as the choice and can provide your own problem statement and solution. Please note it should have relation to solving Covid-19 challenges which is the theme of the hackathon

Q. Do I need to submit the solution while registering for Hackathon? This is one of the fields while applying for Hackathon?

A. No you do not need to submit the solution when you register. You can create your account and then later submit the solution before the deadline

Q. Can I resubmit solution after registering?

A. Yes you can do it any number of times till the deadline for the respective round is not over.

Q. The registration form is asking for a link to where the submission is. What does link mean?

A. AI solutions will consist of jupyter notebooks, datasets, presentations etc. You can put all these in github, Google drive , Dropbox etc and just provide us with that link. Just make sure you give us access to same else we will not be able to evaluation your submission.

Problem Statements

Title: Drug Discovery and Genome Sequencing

Problem Statement

The genome of novel Coronavirus has been sequenced by various countries, and reference of same been built having approximate size of 30kb. India became the fifth country in the world to sequence the genome of the novel Coronavirus, or COVID19, and share its data with the international community. Two sequence from India has been submitted to the NCBI database. Genome data is essential to build tests, find drugs and vaccines. As virus tend to mutate at a high rate and hence can become more pathogenic. Hence understanding of changes in virus genome becomes essential. The study on changes in virus genome can also guide in determining the source of infection and thereby will help in spread of Virus. The study of genome will also help in finding unique regions in the virus genome and which can target for drug development. Drug Development typically takes at least decade to move from idea to market. Also, crystal structures for some of the proteins for coronavirus has been solved. Hence Drug repurposing studies can be carried out using already FDA approved ligand database. We can substantially accelerate this process using AI and make it much cheaper, faster, and more likely to succeed. The objective of this problem statement is to find novel ideas to identify potential drugs and drug targets for the treatment of COVID-2019.

Expected Outcome:

  • AI based tool to identify novel drug targets based on genome data
  • To develop AI based tool for faster screening of available ligand molecules to predict probable lead molecules (Drug Repurposing).

Sample Dataset for Reference

Indian Submissions: Complete Genome

Indian Submissions: Partial CDS

These are links to sample dataset for reference purpose only. Participants are free to use these or other datasets after studying respective licenses.

References of Research papers/Technical documents


Title: Diagnosing COVID-19 using AI-based medical image analyses

Problem Statement

Radiologists have watched the coronavirus disease 2019 (COVID-19) pandemic unfold. Radiology literature suggests a pivotal role for CT/X-RAYas CT/X-Ray findings in Covid-19 patient has pneumonia, and hence medical imaging has high sensitivity for diagnosis of COVID-19. The objective of this statement is to figure out usage of AI in medical imaging modalities for fast and accurate diagnosis of COVID-19

Expected Outcome: Diagnosing or detecting patients infected with COVID19 using chest radiography images

Sample Dataset for Reference

These are links to sample dataset for reference purpose only. Participants are free to use these or other datasets after studying respective licenses

References of Research papers/Technical documents


Title: Public Health Surveillance and Monitoring

Problem Statement

In order to enforce social distancing, it is important to monitor suspicious scenarios like crowd gathering or tracking etc. Usage of AI (Convolution Neural Network) has surpassed traditional Computer Vision techniques and can help automate this pattern recognition. The objective of this problem statement is to find different pattern on input sources like camera, satellite, social platforms which can help identify suspicious activities to stop or track covid-19 spread.

Sample Dataset for Reference

Crowd Counting/Gathering Database:

People Detection and Tracking:

Flu Recognition:

These are links to sample dataset for reference purpose only. Participants are free to use these or other datasets after studying respective licenses

References of Research papers/Technical documents


Title: Pandemic Forecasting

Problem Statement

The number of new cases is increasing day by day around the world. The participants can use the dataset that has information from the states and union territories of India daily and in some case at hourly intervals. In this challenge, you will be predicting the cumulative number of confirmed COVID19 cases in various locations across the world, as well as the number of resulting fatalities, for future dates. Also, this can be combined with social dataset like of Twitter where the first tweet goes back to January 22, 2020. Other parameters of importance could be the impact of weather and India Population Demographics.

Sample Dataset for Reference

Crowd Counting/Gathering Database:

These are links to sample dataset for reference purpose only. Participants are free to use these or other datasets after studying respective licenses

References of Research papers/Technical documents


Title: Data Mining

Problem Statement

With Covid-19 becoming a pandemic the research on same has also accelerated. There are more than 44000 research articles already published and growing. It is important to implement functionalities like Data mining that can help the medical community to develop answers to high priority scientific questions. AI can help mine through news reports and online content from around the world, helping experts recognize anomalies even before it reaches epidemic proportions. The objective is to analyze the existing literature for analysis including question, answering and summarization which helps in getting better and faster insights.

Sample Dataset for Reference

Crowd Counting/Gathering Database:

These are links to sample dataset for reference purpose only. Participants are free to use these or other datasets after studying respective licenses

References of Research papers/Technical documents


Title: Other/Open House Challenge

Problem Statement

The participants may bring their own problem statement along with datasets and apply with solutions with the following priorities (but not limited to):

  • To achieve better (More Accurate) and Faster Turnaround time forTesting and results.
  • To identify, track and forecast outbreaks.
  • To develop the Drug Re-purposing Simulations leading to New Drug Discovery.
  • To develop the Simulations/Solutions using Traditional (AYUSH) Medicines.
  • To create Chat Bot with multiple regional language supporting Conversational AI Techniques.
  • To develop AI based identification of non-complying or infected individuals.
  • To create, Train and Deploy Robots to sterilize, Deliver Food and Supplies.
  • To deploy Drones to monitor sites, announce policy measures and to deliver medical supplies in the infected regions/areas;
    To enable automation of COVID 19 Health care Claims for Ayushman Bharat Program.

About Us

C-DACThe Centre for Development of Advanced Computing (C-DAC) is an autonomous Scientific Society under the Ministry of Communications & Information Technology, Government of India. Set up in 1988, as India's national initiative for Design, Development and Delivery of High Performance Computing (Supercomputer) Systems and solutions based on parallel processing technology, C-DAC has over the years expanded its activities. It has transferred the expertise acquired to provide Advanced Computing solutions in the state-of-the-art areas of ICT.

More about C-DAC: https://www.cdac.in

C-DACNational Supercomputing Mission (NSM) is a proposed plan by Government of India to empower India's National Academic and R&D institutions spread over the country by installing a vast supercomputing grid comprising of High-Performance Computing facilities. Another goal is to develop applications of National Importance. For these applications the entire compute needs are provided through NSM. The Mission also includes development of highly professional HPC-Aware Human Resource for meeting challenges of development of these applications. The Mission implementation would bring supercomputing within the reach of the large Scientific & Technology community in the country and enable the country with a capacity of solving multi-disciplinary grand challenge problems. The Mission is being implemented and steered jointly by the Ministry of Electronics and Information Technology (MeitY) and Department of Science and Technology (DST), Government of India.

More about NSM: https://www.nsmindia.in

C-DACNVIDIA's (NASDAQ:NVDA) invention of the GPU in 1999 sparked the growth of the PC gaming market, redefined modern computer graphics and revolutionized parallel computing. More recently, GPU deep learning ignited modern AI - the next era of computing - with the GPU acting as the brain of computers, robots and self-driving cars that can perceive and understand the world.

More information on NVIDIA: http://nvidianews.nvidia.com

C-DACOpenACC.org is a non-profit organization founded to help scientists and researchers do more science and less programming by providing a high-level directives-based programming model for High Performance Computing. The OpenACC Organization is dedicated to helping the research and developer community advance science by expanding their accelerator and parallel computing skills. They have 3 areas of focus: participating in computing ecosystem development, providing training and education on programming models, resources and tools, and developing the OpenACC specification. The organization is run by academic and industry members in collaboration with OpenACC user community.

More information on NVIDIA: https://www.openacc.org